Mistral Large 2.1 vs Nova Lite vs Claude Haiku 3.5
Nova Lite comes out ahead, 75 to 44 and 25 on our weighted score, and it is the cheaper option too.
Mistral AIMistral Large 2.1
25/100- ECI128.6
- Price$2.00 / $6.00
- Context131K
- Our pick
AmazonNova Lite
75/100- ECI—
- Price$0.06 / $0.24
- Context300K
AnthropicClaude Haiku 3.5
44/100- ECI127.0
- Price$0.80 / $4.00
- Context200K
Nova Lite is our pick
Nova Lite is the better all-round choice, scoring 75/100 against Claude Haiku 3.5 (44) and Mistral Large 2.1 (25). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNova LiteNova Lite $0.105 · Claude Haiku 3.5 $1.60 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend)
- Longest contextNova LiteNova Lite 300,000 · Claude Haiku 3.5 200,000 · Mistral Large 2.1 131,072 tokens
- Widest inputsNova LiteMistral Large 2.1: Text · Nova Lite: Text, Images, PDFs, Video · Claude Haiku 3.5: Text, Images, PDFs
- Self-hostingMistral Large 2.1Publishes downloadable weights
| Measure | Weight | Mistral Large 2.1 | Nova Lite | Claude Haiku 3.5 |
|---|---|---|---|---|
| Price | 50% | 26 | 92 | 38 |
| Inputs & features | 30% | 25 | 70 | 60 |
| Context window | 20% | 25 | 39 | 32 |
| Overall | 100% | 25/100 | 75/100 | 44/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Mistral Large 2.1Mistral AI | Nova LiteAmazon | Claude Haiku 3.5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 128.6 (best) | — | 127.0 |
| ECI rank | #142 of 165 (best) | — | #147 of 165 |
| GPQA DiamondGraduate-level science questions | 51.3% (best) | — | 38.1% |
| OTIS Mock AIME 2024–2025Competition mathematics | 7.8% (best) | — | 4.3% |
| Price per million tokens | |||
| Input | $2.00 | $0.06 (best) | $0.80 |
| Output | $6.00 | $0.24 (best) | $4.00 |
| Cached input | — | $0.015 | — |
| Blended (3:1) | $3.00 | $0.105 (best) | $1.60 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Official Amazon Bedrock API | Median of 3 providers |
| Limits | |||
| Context window | 131,072 tokens | 300,000 tokens (best) | 200,000 tokens |
| Max output | 16,384 tokens (best) | 10,000 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | amazon.nova-lite-v1:0 | — |
| API providers | 2 | 8 (best) | 4 |
| Released | Nov 18, 2024 | Dec 3, 2024 | Oct 22, 2024 |
| Knowledge cutoff | Nov 2024 | Oct 2024 | Jul 31, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mistral Large 2.1$32.00
- Nova Lite$1.08
- Claude Haiku 3.5$16.00
Which should you choose?
Which is better: Mistral Large 2.1, Nova Lite or Claude Haiku 3.5?
Nova Lite is the better all-round choice, scoring 75/100 against Claude Haiku 3.5 (44) and Mistral Large 2.1 (25). It leads on price, inputs & features and context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Mistral Large 2.1, Nova Lite or Claude Haiku 3.5?
Nova Lite is cheaper at $0.06 input / $0.24 output per million tokens (official Amazon Bedrock API price). Claude Haiku 3.5 costs $0.80 input / $4.00 output per million tokens (median across 3 API providers); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.105 per million tokens for Nova Lite versus $1.60 for Claude Haiku 3.5 (15× as much) and $3.00 for Mistral Large 2.1 (29× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Mistral Large 2.1 has an ECI of 128.6, Nova Lite has not been scored yet and Claude Haiku 3.5 has an ECI of 127.0.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Large 2.1, Nova Lite and Claude Haiku 3.5 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Nova Lite has the largest context window at 300,000 tokens, against 200,000 for Claude Haiku 3.5 and 131,072 for Mistral Large 2.1. Maximum output per response: Mistral Large 2.1 up to 16,384, Nova Lite up to 10,000, Claude Haiku 3.5 up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Mistral Large 2.1 accepts text; Nova Lite accepts text, images, PDFs and video; Claude Haiku 3.5 accepts text, images and PDFs. Nova Lite handles the widest range of inputs.
Are any of these open source?
Mistral Large 2.1 publishes its weights and can be self-hosted; Nova Lite and Claude Haiku 3.5 is proprietary.
Which is newer?
Nova Lite is the newest, released Dec 3, 2024. Mistral Large 2.1 came out Nov 18, 2024; Claude Haiku 3.5 came out Oct 22, 2024. Knowledge cutoff: Mistral Large 2.1 Nov 2024, Nova Lite Oct 2024, Claude Haiku 3.5 Jul 31, 2024.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
